TensorRTFlags enum

A flag for OrtProvider.tensorrt. TensorRT provides optimized inference on NVIDIA GPUs with additional optimizations.

Inheritance
Implemented types
Available extensions

Values

useNone → const TensorRTFlags

Use default TensorRT provider options

const TensorRTFlags(0x000)
useFp16 → const TensorRTFlags

Enable TensorRT FP16 (half precision) mode Faster inference with minimal accuracy loss

const TensorRTFlags(0x001)
useInt8 → const TensorRTFlags

Enable TensorRT INT8 quantization Even faster with calibration, more accuracy loss

const TensorRTFlags(0x002)
forceSequentialEngineBuild → const TensorRTFlags

Force sequential engine building More stable but slower model initialization

const TensorRTFlags(0x004)

Properties

hashCode int
The hash code for this object.
no setterinherited
index int
A numeric identifier for the enumerated value.
no setterinherited
name String

Available on Enum, provided by the EnumName extension

The name of the enum value.
no setter
runtimeType Type
A representation of the runtime type of the object.
no setterinherited
value int
no setteroverride

Methods

noSuchMethod(Invocation invocation) → dynamic
Invoked when a nonexistent method or property is accessed.
inherited
toString() String
A string representation of this object.
inherited

Operators

operator ==(Object other) bool
The equality operator.
inherited

Constants

values → const List<TensorRTFlags>
A constant List of the values in this enum, in order of their declaration.